Every face gets its own finish line

The same movement, scored two ways: one fixed target for every child, or a target learned from this child's own face. Runs entirely in your browser.

Nothing is uploaded.Frames are read by the model inside this tab and thrown away.

Camera

Try it on your own face
Your browser will ask permission first. Nothing is recorded or uploaded.
Calibrationnot yet done
Resting baseline  L / R— / —
Personal best  L / R— / —
Raw signal  L / R— / —

Exercise

One target for everyone

One absolute value for everyone. A weak side may never reach it, however hard the child tries.

LEFT
0%
RIGHT
0%
—

A target for this child

Each side is measured against its own resting face and its own best. Beating yourself counts as winning.

LEFT
0%
RIGHT
0%
—

The buddy has it too. One side of its face is stiff, and it loosens up only as the child's own best rises — so nobody practises alone in front of a mirror.

What changes. The weak side is never asked to match the strong side — only to beat its own best. Progress is the reward, so a child with a real asymmetry still finishes a session having succeeded, and the target rises quietly as recovery happens.